查询和过滤
可以使用两种结构化语句： 结构化查询（Query DSL）和结构化过滤（Filter DSL）。 查询与过滤语句非常相似，但是它们由于使用目的不同而稍有差异。

复合查询

查全部

  1. GET /ecommerce/product/_search
  2. {
  3.  "query": { "match_all": {} }
  4. }

查询不存在的字段

  1. GET index/_search
  2. {
  3.   "query": {
  4.     "bool": {
  5.       "must_not": {
  6.            "exists":{"field":"filedX"}
  7.       }
  8.       }
  9.   }
  10. }

bool 查询

该模板适用于所有情况，尤其适用于侧边栏多级多条件联合查询

  1. {
  2.     "query": {
  3.         "bool": {
  4.             "must": [
  5.                 {
  6.                     "match": {
  7.                         "countryArea": "United States"
  8.                     }
  9.                 },
  10.                 {
  11.                     "bool": {
  12.                         "should": [
  13.                             {
  14.                                 "match": {
  15.                                     "sponsor": "National Science Foundation"
  16.                                 }
  17.                             },
  18.                             {
  19.                                 "match": {
  20.                                     "sponsor": "David and Lucile Packard Foundation"
  21.                                 }
  22.                             }
  23.                         ],
  24.                         "minimum_should_match": 1
  25.                     }
  26.                 },
  27.                 {
  28.                     "bool": {
  29.                         "should": {
  30.                             "nested": {
  31.                                 "path": "researchAreas",
  32.                                 "query": {
  33.                                     "bool": {
  34.                                         "should": [
  35.                                             {
  36.                                                 "match": {
  37.                                                     "researchAreas.subjectName": "Arts and Humanities"
  38.                                                 }
  39.                                             },
  40.                                             {
  41.                                                 "match": {
  42.                                                     "researchAreas.subjectName": "Ecology"
  43.                                                 }
  44.                                             }
  45.                                         ],
  46.                                         "minimum_should_match": 1
  47.                                     }
  48.                                 }
  49.                             }
  50.                         }
  51.                     }
  52.                 }
  53.             ],
  54.             "must_not": {
  55.                 "match": {
  56.                     "fundingType": "Program or Curriculum Development or Provision"
  57.                 }
  58.             }
  59.         }
  60.     }
  61. }

range

gt: greater than 大于
gte: greater than or equal 大于等于
lt: less than 小于
lte: less than or equal 小于等于

  1. GET /salemgr_user_bigtable/_doc/_search?
  2. {
  3.     "from":0,
  4.     "query":{
  5.         "bool":{
  6.             "filter":[
  7.                         {
  8.                           "range":{
  9.                             "data_officeloginon":{
  10.                               "lt":0
  11.                             }
  12.                           }
  13.                         }
  14.             ]
  15.         }
  16.     },
  17.     "size":20
  18. }

bool过滤

一条过滤语句会询问每个文档的字段值是否包含着特定值：

  • created 的日期范围是否在 2013 到 2014 ?
  • status 字段中是否包含单词 “published” ?
  • lat_lon 字段中的地理位置与目标点相距是否不超过10km ?
    1. GET / ecommerce / product / _search 
    2. {
    3.   "query": {
    4.       "bool": {
    5.           "must": {
    6.               "match": {
    7.                   "name": "yagao" 
    8.               }
    9.           },
    10.           "filter": {
    11.               "range": {
    12.                   "price": {
    13.                       "gt": 25
    14.                   } 
    15.               }
    16.           }
    17.       }
    18.   }
    19. }

    过滤后排序

    1. {
    2.   "size":5,
    3.   "query":{
    4.       "bool":{
    5.           "filter":[
    6.               {
    7.                   "range":{
    8.                       "startTime":{
    9.                           "from":1517046960000,
    10.                           "to":1517048760000
    11.                       }
    12.                   }
    13.               }
    14.           ]
    15.       }
    16.   },
    17.   "sort":[
    18.       {
    19.           "startTime":{
    20.               "order":"desc"
    21.           }
    22.       }
    23.   ]
    24. }

    脚本排序

    ```java String str = “(doc[‘heat’].size()==0 ? 0 : doc[‘heat’].value) + “ +
    1.   "(doc['unfold'].size()==0 ? 0 : doc['unfold'].value)";
    Script script = new Script(str);

ScriptSortBuilder scriptSortBuilder = SortBuilders .scriptSort(script, ScriptSortBuilder.ScriptSortType.NUMBER) .order(SortOrder.DESC); searchSourceBuilder.sort(scriptSortBuilder);

  1. <a name="MZr8P"></a>
  2. ## multi_match
  3. `multi_match`查询提供了一个简便的方法用来对多个字段执行相同的查询。
  4. <a name="NSeFp"></a>
  5. # 聚合
  6. <a name="24bOi"></a>
  7. ## 按组内字段排序
  8. AggregationBuilder aggregation =<br />    AggregationBuilders<br />        .terms("agg").field("gender")<br />        .subAggregation(<br />            AggregationBuilders.topHits("top")<br />                .explain(true)<br />                .size(1)<br />                .from(10)<br />                .sort("sortFiled", SortOrder.ASC)<br />        );
  10. <a name="bUTCn"></a>
  11. ## 按聚合后指标排序
  13. 1. 通过key排序
  15. TermsAggregationBuilder termsAggs = AggregationBuilders._terms_("聚合名称").field("分组字段")<br />        .order(BucketOrder._key_(true));
  17. 2. 文档数聚合
  19. .order(BucketOrder.count(true))
  20. <a name="2451b9c1"></a>
  21. ## 根据聚合结果排序  根据字聚合 responseTime.avg
  22. ```json
  23. {
  24.   "query" : {
  25.     "bool" : {
  26.       "filter" : [
  27.         {
  28.           "term" : {
  29.             "type" : {
  30.               "value" : "URL",
  31.               "boost" : 1.0
  32.             }
  33.           }
  34.         }
  35.       ]
  36.     }
  37.   },
  38.   "aggregations" : {
  39.     "CATEGORY" : {
  40.       "terms" : {
  41.         "field" : "name",
  42.         "size" : 5,
  43.         "order" : {"responseTime.avg" : "asc" }
  44.       },
  45.       "aggregations" : {
  46.         "responseTime" : {
  47.           "extended_stats" : {
  48.             "field" : "durationInMillis",
  49.             "sigma" : 2.0
  50.           }
  51.         },
  52.         "error" : {
  53.           "sum" : {
  54.             "script" : {
  55.               "inline" : "def errorTemp=doc['status'].value; if(errorTemp=='0'){return 0;}else{return 1;}",
  56.               "lang" : "painless"
  57.             }
  58.           }
  59.         },
  60.         "apdex" : {
  61.           "avg" : {
  62.             "script" : {
  63.               "inline" : "def responseTemp=doc['durationInMillis'].value; if(responseTemp>params.threshold){return 0.5;}else{return 1;}",
  64.               "lang" : "painless",
  65.               "params" : {
  66.                 "threshold" : 20.0
  67.               }
  68.             }
  69.           }
  70.         },
  71.         "errorRate" : {
  72.           "percentile_ranks" : {
  73.             "script" : {
  74.               "inline" : "def errorTemp=doc['status'].value; if(errorTemp=='0'){return 1;}else{return 0;}",
  75.               "lang" : "painless"
  76.             },
  77.             "values" : [
  78.               0.0
  79.             ],
  80.             "keyed" : true,
  81.             "tdigest" : {
  82.               "compression" : 100.0
  83.             }
  84.           }
  85.         }
  86.       }
  87.     }
  88.   }
  89. }

按聚合名称标识对桶进行排序
AggregationBuilders
.terms(“genders”)
.field(“gender”)
.order(BucketOrder.aggregation(“avg_height”, false))
.subAggregation(
AggregationBuilders.avg(“avg_height”).field(“height”)
)

按多个聚合指标对桶进行排序

AggregationBuilders
.terms(“genders”)
.field(“gender”)
.order(BucketOrder.compound( // in order of priority:
BucketOrder.aggregation(“avg_height”, false), // sort by sub-aggregation first
BucketOrder.count(true))) // then bucket count as a tie-breaker
.subAggregation(
AggregationBuilders.avg(“avg_height”).field(“height”)
)

聚合nested

GET audio/info/_search
{
  "size": 0, 
  "query":{
    "bool": {
      "must": [
        {
          "range": {
            "info.inputTime": {
              "gte": "2019-07-01 05:51:47",
              "lte": "2019-07-09 09:59:59"
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "wordgroup": {
      "nested": {
        "path": "wordFrequency"
      },
      "aggs": {
        "word": {
          "terms": {
            "field": "wordFrequency.keyword",
            "size": 50,
            "exclude": ["这个"], 
            "order": {
              "wordnum.value": "desc"
            }
          },
          "aggs": {
            "wordnum": {
              "sum": {
                "field": "wordFrequency.count"
              }
            }
          }
        }
      }
    }
  }
}

GET /community_user_bigtable/_doc/_search?{
“size”:0,
“_source”:false,
“aggs”:{
“class_aggs”:{
“terms”:{
“field”:”classid”,
“order”: [{“isfillpaper_sum”: “desc”} ]
},
“aggs”:{
“isfillpaper_sum”:{
“sum”:{
“field”:”isfillpaper”
}
},
“wechat_sum”:{

“sum”:{
“field”:”isaddwechat”
}
},
“login_filter”:{
“filter”:{
“range”: {
“data_logintime”: {
“gte”: 0
}
}
}
},
“login_sum2”:{
“filter”:{
“range”: {
“data_logintime”: {
“lte”: 0
}
}
},
“aggs”:{
“term”:{
“sum”:{
“field”:”isfillpaper”
}
}
}
}
}
}
}
}